Bruno Silva

Hello curious mind, welcome to my blog!

My name is Bruno Silva, I am a second year Ph.D. student at University of Aveiro. My main line of research revolves around using Meta Reinforcement-Learning for Contact-Rich Human-Robot collaboration (HRC) tasks. I argue that robots are held back in HRC due to a lack of proactive ability that is present in Human to Human collaboration (HHC). To that end, during my FCT Scholarship, my main goal is to create Meta RL agents capable of controlling robots to collaborate with humans in dynamic and unstructured environments and endow said agents with latent-future prediction capabilities to close the gap between HRC and HHC.

As of November 2025, I finished a RL Specialization in Coursera, which gave me the necessary theoretical background to further pursue my endeavors in RL. I’m currently assessing the state of the art in the fields of :”Deep RL”,”RL in Contact-Rich Tasks” and “Model-based RL”. I’m also learning how to use Nvidia’s IsaacLab for my future experiments.